HuatuoGPT-o1-72B: benchmark results
Provider: Other. Released 2024-12-30. Access: Open.
Aggregate Rating 1598 ± 32, rank #1031 of 10916 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GPAgentBench-2K - Missed Referral Rate | 39.3 | Missed referral rate (%; referral-required cases the agent m | 100 |
| BRIDGE Medical Leaderboard - Zero-Shot | 41.01 | Average Performance (%) | 83.8 |
| BRIDGE Medical Leaderboard - Few-Shot | 50.21 | Average Performance (%) | 82 |
| BRIDGE Medical Leaderboard - CoT | 38.15 | Average Performance (%) | 78.4 |
| LLMEval-Med - Medical Reasoning | 56.86 | Usability rate: share of responses a GPT-4o judge scores 4 o | 66.7 |
| GPAgentBench-2K - Diagnosis Accuracy | 62.3 | Diagnosis accuracy (%; final diagnosis judged correct by a G | 65 |
| PopAnesQA - General | 80.5 | Accuracy (%) | 62.5 |
| LLMEval-Med - Medical Language Understanding | 49.45 | Usability rate: share of responses a GPT-4o judge scores 4 o | 50 |
| LLMEval-Med - Medical Text Generation | 45.36 | Usability rate: share of responses physicians rate usable on | 50 |
| LLMEval-Med - Medical Safety and Ethics | 56.27 | Usability rate: share of responses a GPT-4o judge scores 4 o | 45.8 |
| GPAgentBench-2K - Treatment Score | 33.2 | Treatment score (%; prescribed treatment scored by a GPT-5.4 | 45 |
| PopAnesQA | 69.66 | Accuracy (%) | 43.8 |
Interactive version: theaggregate.ai/model?slug=huatuogpt-o1-72b · How It Works · Data refreshed daily, snapshot 2026-11-08.